An, P., 2018. Path optimization method of autonomous intelligent obstacle avoidance for multi-joint submarine robot. In: Ashraf, M.A. and Chowdhury, A.J.K. (eds.), Coastal Ecosystem Responses to Human and Climatic Changes throughout Asia.
A multi-joint submarine robot could not avoid obstacles in real time under the complex environment of the seafloor. To address this problem, a method for path optimization of autonomous intelligent obstacle avoidance by the multi-joint submarine robot was proposed. First, a kinematic analysis of the multi-joint submarine robot was carried out. The joint space interpolation algorithm was used for trajectory planning of its robotic arm. The partial identification samples at the starting point and the target point part were set. A similarity matrix was used for assigning unlabeled samples, and all labeled samples were given to a support vector machine. A genetic algorithm was used to optimize the parameters of the support vector machines. The experimental result shows that the proposed method realizes the requirement of autonomous intelligent real-time obstacle avoidance and the path is the shortest.